Skip to main content

MiMo-V2-Pro

XiaomiProprietary

Description

MiMo-V2-Pro is Xiaomi's flagship foundation model built for real-world agentic workloads. A Mixture-of-Experts model with over 1T total parameters and 42B active, roughly 3x larger than MiMo-V2-Flash. Inherits the Hybrid Attention mechanism with a 7:1 ratio and supports up to 1M-token context. Optimized for coding and agent tasks through post-training scaling across diverse agent scenarios, with native support for complex tool calling and multi-step reasoning.

Release Date
2026-03-18
Parameters
1.0T
Context Length
1.0M
Modalities
text

Capability Radar

38
general
43
coding
87
reasoning
60
scienceest.
80
agents
0
multimodal

Science uses a reasoning proxy when dedicated science benchmarks are unavailable.

Rankings

Domain#RankScoreSource
Agentic Capability23
63.0
LS
Code Ranking67
73.0
AA
General Ranking39
78.0
AA
Science44
72.0
AA

Benchmark Scores (LLM Stats)

Agents

GDPval-AA1426.00 / 3000SR
DeepSearchQA86.7%SR
PinchBench81.0%SR
Claw-Eval61.5%SR
Terminal-Bench 2.057.1%SR

Code

SWE-Bench Verified78.0%SR
SWE-bench Multilingual71.7%SR

Communication

Tau2 Telecom96.8%SR

AA Evaluation Indices

Intelligence Index
40.3
Tau2
1.0
Gpqa
0.9
Ifbench
0.7
Lcr
0.6
Scicode
0.4
Terminalbench Hard
0.4
Hle
0.3

LLM Stats Category Scores

Legal
100
Finance
100
General
100
Agents
100
Reasoning
100
Communication
100
Search
90
Frontend Development
80
Tool Calling
80
Code
70
Coding
70

Pricing

Input Price$1 / 1M tokens
Output Price$3 / 1M tokens
Blended Price (3:1)$1.5 / 1M tokens
Cache Read Price$0.2 / 1M tokens

Speed

Tokens/sec52.2
Time to First Token1.73s
Time to Answer57.82s

Provider Price Ranking

Provider Price Ranking

8 providers

Cheapest: XiaomiMost Expensive: NovitaAI
ProviderInputOutput
1XiaomiPRIMARY
$1
$3
2NanoGPT
$1
$3
3OpenCode Go
$1
$3
4ZenMux
$1
$3
5Kilo Gateway
$1
$3
6Vercel AI Gateway
$1
$3
7LLM Gateway
$1
$3
8NovitaAI
$2
$6

Compare pricing across different API providers for this model.

External Sources